perception

AI and robotics

The process, or the subsystem, by which an agentintelligent agent, n.: In AI theory, a decision-maker, such as a robot, a self-driving car, a chess program or a helpful piece of software, that notices what is going on around it and responds in ways that serve its goals. maps raw sensor data to representations it can reason and act on: detected objects and their positions, free space, speech transcripts, the poses of nearby people. In textbook terms, perception supplies the agent's estimate of the world statestate, n.: A snapshot of the situation an AI agent is in — for a chess program, the arrangement of pieces and whose turn it is — containing what it needs to decide what to do next.; in robotics and autonomous vehiclesautonomous vehicle, n.: A vehicle, usually a car, truck or shuttle, that can drive itself, sensing the road, deciding what to do and steering, braking and accelerating with no human driving. it is the first stage of the classic perception–prediction–planning–control stack, usually combining cameras, lidarlidar, n.: A sensor that measures distances by firing laser pulses and timing their reflections, building a 3D picture of its surroundings out of millions of points; widely used on robots and self-driving cars., radar and microphones through sensor fusionsensor fusion, n.: Combining readings from several different sensors, such as cameras, radar, lidar, GPS and motion sensors, to get a more accurate and reliable picture than any one sensor gives alone.. Machine perception spans computer visioncomputer vision, n.: The part of AI that lets computers make sense of images and video: recognizing faces, reading signs, spotting tumors on scans or judging how far away a car is., speech recognitionspeech recognition, n.: Technology that turns spoken words into written text, as when a phone transcribes a voice message or captions appear automatically under a video. and audio analysis, touch (tactile sensingtactile sensing, n.: Giving robots a sense of touch, with sensors in fingertips or skin that feel pressure, texture, vibration and slipping, so they can handle objects gently and securely.) and proprioceptionproprioception, n.: A robot's sense of its own body: where its joints are, how fast they are moving and how hard its motors are pushing, measured by internal sensors rather than cameras.. Since the late 2010s, separate hand-built perception modules have increasingly given way to large pretrained encoders and multimodalmultimodal AI, n.: AI that can take in or produce more than one kind of information, such as text, images, sound and video, so you can show it a photo and ask questions about it. foundation modelsfoundation model, n.: A very large AI model, built once at great cost from vast amounts of text, images or code gathered mostly from the internet, that many products then reuse as their starting point, from chatbots to coding tools..

The planner was fine; the crash traced back to perception classifying the overturned truck as background.

Cognitive science

The faculty by which humans and animals turn the signals reaching their senses into an experience of objects, events and surroundings. Theories of human perception, as unconscious inference from ambiguous signals (Hermann von Helmholtz), as direct pickup of information (James J. Gibson) or as predictionpredictive processing, n.: The idea that the brain is a prediction machine: it constantly guesses what its senses will report next and learns mainly from its mistakes, so what we perceive is largely its best guess., have repeatedly shaped machine approaches, and comparisons of model and human perception (illusions, shape versus texture bias, adversarial imagesadversarial example, n.: An input altered on purpose, often too slightly for people to notice, so that an AI model gets it badly wrong — like a panda photo that a classifier confidently calls a gibbon.) remain an active research area.